struct event_pair
{
  cudaEvent_t start;
  cudaEvent_t end;
};


inline void check_launch(char * kernel_name)
{
  cudaThreadSynchronize();
  if(cudaGetLastError() == cudaSuccess)
  {
    printf("done with %s kernel\n",kernel_name);
  }
  else
  {
    printf("error on %s kernel\n",kernel_name);
    exit(1);
  }
}


inline void start_timer(event_pair * p)
{
  cudaEventCreate(&p->start);
  cudaEventCreate(&p->end);
  cudaEventRecord(p->start, 0);
}


inline void stop_timer(event_pair * p, char * kernel_name)
{
  cudaEventRecord(p->end, 0);
  cudaEventSynchronize(p->end);
  
  float elapsed_time;
  cudaEventElapsedTime(&elapsed_time, p->start, p->end);
  printf("%s took %.1f ms\n",kernel_name, elapsed_time);
  cudaEventDestroy(p->start);
  cudaEventDestroy(p->end);
}

bool AlmostEqual2sComplement(float A, float B, int maxUlps)
{
    // Make sure maxUlps is non-negative and small enough that the
    // default NAN won't compare as equal to anything.
    // assert(maxUlps > 0 && maxUlps < 4 * 1024 * 1024);
    int aInt = *(int*)&A;
    // Make aInt lexicographically ordered as a twos-complement int
    if (aInt < 0)
        aInt = 0x80000000 - aInt;
    // Make bInt lexicographically ordered as a twos-complement int
    int bInt = *(int*)&B;
    if (bInt < 0)
        bInt = 0x80000000 - bInt;
    int intDiff = abs(aInt - bInt);
    if (intDiff <= maxUlps)
        return true;
    return false;
}